Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4420 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.8539. Min Act: -0.1700
Data Index: 8424001 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.6036. Min Act: -0.1700
Data Index: 1926081 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.5410. Min Act: -0.1700
Data Index: 1506256 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.5253. Min Act: -0.1700
Data Index: 6601902 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.5410. Min Act: -0.1700
Data Index: 8245884 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.5253. Min Act: -0.1700
Data Index: 533854 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4940. Min Act: -0.1700
Data Index: 3039938 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4783. Min Act: -0.1700
Data Index: 5861105 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4627. Min Act: -0.1700
Data Index: 4276430 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4627. Min Act: -0.1700
Data Index: 1815783 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4470. Min Act: -0.1700
Data Index: 3655931 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4470. Min Act: -0.1700
Data Index: 8600389 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4000. Min Act: -0.1700
Data Index: 3661492 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5022845 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4000. Min Act: -0.1700
Data Index: 3064431 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4157. Min Act: -0.1700
Data Index: 59083 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.3843. Min Act: -0.1700
Data Index: 4939073 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.4000. Min Act: -0.1700
Data Index: 4206410 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.3843. Min Act: -0.1700
Data Index: 4786844 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8539. Min Range: -3.8539
Max Act: 3.3686. Min Act: -0.1700
Data Index: 8424002 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19